Value of Quantitative CTTA in Differentiating Malignant From Benign Bosniak III Renal Lesions on CT Images
- 26 June 2021
- journal article
- research article
- Published by Wolters Kluwer Health in Journal of Computer Assisted Tomography
- Vol. 45 (4) , 528-536
Abstract
Objective: The aim of this study was to investigate whether computed tomography texture analysis can differentiate malignant from benign Bosniak III renal lesions on computed tomography (CT) images. Methods: This retrospective case-control study included 45 patients/lesions (22 benign and 23 malignant lesions) with Bosniak III renal lesions who underwent CT examination. Axial image slices in the unenhanced phase, corticomedullary phase, and nephrographic phase were selected and delineated manually. Computed tomography texture analysis was performed on each lesion during these 3 phases. Histogram-based, gray-level co-occurrence matrix, and gray-level run-length matrix features were extracted using open-source software and analyzed. In addition, receiver operating characteristic curve was constructed, and the area under the receiver operating characteristic curve (AUC) of each feature was constructed. Results: Of the 33 extracted features, 16 features showed significant differences (P < 0.05). Eight features were significantly different between the 2 groups after Holm-Bonferroni correction, including 3 histogram-based, 4 gray-level co-occurrence matrix, and 1 gray-level run-length matrix features (P < 0.01). The texture features resulted in the highest AUC of 0.769 ± 0.074. Renal cell carcinomas were labeled with a higher degree of lesion gray-level disorder and lower lesion homogeneity, and a model incorporating the 3 most discriminative features resulted in an AUC of 0.846 ± 0.058. Conclusions: The results of this study showed that CT texture features were related to malignancy in Bosniak III renal lesions. Computed tomography texture analysis might help in differentiating malignant from benign Bosniak III renal lesions on CT images.Keywords
This publication has 49 references indexed in Scilit:
- Chronic Kidney Disease After Nephrectomy in Patients with Small Renal Masses: A Retrospective Observational AnalysisEuropean Urology, 2012
- A Non–Cancer-Related Survival Benefit Is Associated With Partial NephrectomyEuropean Urology, 2012
- Machine learning study of several classifiers trained with texture analysis features to differentiate benign from malignant soft‐tissue tumors in T1‐MRI imagesJournal of Magnetic Resonance Imaging, 2010
- MaZda—A software package for image texture analysisComputer Methods and Programs in Biomedicine, 2009
- Radiographic surveillance of minimally and moderately complex renal cystsBJU International, 2009
- The Bosniak classification of renal cystic massesBJU International, 2005
- Chronic Kidney Disease and the Risks of Death, Cardiovascular Events, and HospitalizationNew England Journal of Medicine, 2004
- Follow-Up CT of Moderately Complex Cystic Lesions of the Kidney (Bosniak Category IIF)American Journal of Roentgenology, 2003
- Textural analysis of contrast‐enhanced MR images of the breastMagnetic Resonance in Medicine, 2003
- Percutaneous Biopsy of Renal Masses: Sensitivity and Negative Predictive Value Stratified by Clinical Setting and Size of MassesAmerican Journal of Roentgenology, 2003